# Gemma 2 27B vs Mistral Nemo

> Gemma 2 27B is the stronger model overall, scoring 29.2 to 25.9 on the Noometry Index. Mistral Nemo costs 4.3× less per token, which makes it the better buy when Gemma 2 27B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-2-27b-vs-mistral-nemo
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Gemma 2 27B scores higher in 2 categories and Mistral Nemo in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 2 27B leads 44.4 to 28.6.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 10.8% for Mistral Nemo.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Mistral Nemo accepts more context: 128K tokens versus 8K.

## Snapshot

| | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 29.2 | 25.9 |
| Rank | 302 | 332 |
| Context | 8K | 128K |
| Input $/M | $0.65 | $0.15 |
| Output $/M | $0.65 | $0.15 |
| Weights | Open | Open |

## Coding

- Gemma 2 27B: 33.5 (#243)
- Mistral Nemo: —

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| LMArena Coding | 1211 | — |
| BigCodeBench Complete | 52.5% | — |

## Agentic & Tool Use

- Gemma 2 27B: —
- Mistral Nemo: 23.3 (#118)

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.6% |
| BALROG | — | 17.6% |

## Reasoning

- Gemma 2 27B: 14.8 (#313)
- Mistral Nemo: 19.9 (#230)

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| DTBench | 48% | 48.6% |
| Epoch Capabilities Index | 122.06 | 118.63 |
| LiveBench Reasoning | 28.1% | — |
| LMArena Hard Prompts | 1199 | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| LiveBench | 38.2% | — |
| PIQA | — | 83.5% |

## Math

- Gemma 2 27B: 10.0 (#306)
- Mistral Nemo: 23.5 (#263)

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| MATH Level 5 | 27.9% | 10.8% |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| LMArena Math | 1212 | — |
| GSM8K | — | 84.2% |

## Knowledge

- Gemma 2 27B: 18.9 (#275)
- Mistral Nemo: 12.3 (#293)

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| GPQA Diamond | 36.5% | 29.9% |
| Confabulations | 27.1% | — |
| LMArena Expert | 1172 | — |
| BoolQ | — | 82.5% |
| MMLU | 75.7% | — |

## Multilingual

- Gemma 2 27B: 38.8 (#221)
- Mistral Nemo: —

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1217 | — |
| LMArena Chinese | 1221 | — |
| LMArena French | 1246 | — |
| LMArena German | 1209 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1174 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1228 | — |

## Instruction Following

- Gemma 2 27B: 60.7 (#244)
- Mistral Nemo: —

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| LiveBench Instruction Following | 58.1% | — |
| LMArena Instruction Following | 1206 | — |

## Long Context

- Gemma 2 27B: 37.3 (#213)
- Mistral Nemo: —

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| LMArena Longer Query | 1231 | — |

## Writing & Preference

- Gemma 2 27B: 44.4 (#220)
- Mistral Nemo: 28.6 (#291)

| Benchmark | Gemma 2 27B | Mistral Nemo |
|---|---|---|
| LMArena Text | 1231 | — |
| LMArena Creative Writing | 1241 | — |
| EQ-Bench Creative Writing | — | 881 |
| LMArena Multi-Turn | 1224 | — |
| LiveBench Language | 32.6% | — |

## FAQ

### Is Gemma 2 27B better than Mistral Nemo?

Gemma 2 27B is the stronger model overall, scoring 29.2 to 25.9 on the Noometry Index. Mistral Nemo costs 4.3× less per token, which makes it the better buy when Gemma 2 27B's lead doesn't matter for your workload.

### Which is cheaper, Gemma 2 27B or Mistral Nemo?

Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.

### Which has the bigger context window?

Mistral Nemo does, with 128K tokens against 8K.

### How many benchmarks do Gemma 2 27B and Mistral Nemo share?

4 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Mistral Nemo has 10.